Machine learning models combining pre- and intraoperative data achieved an AUROC of 0.896 (95% CI 0.878-0.914) for predicting postoperative AKI, offering limited gain over preoperative data alone.
Cohort (n=46,204)
Does adding intraoperative data to preoperative data improve machine learning prediction of postoperative AKI in adults undergoing noncardiac surgery?
Preoperative tabular machine learning models provide excellent prediction of postoperative AKI in noncardiac surgery, with intraoperative data adding limited incremental discriminative value.
Effect estimate: AUROC 0.896 (95% CI 0.878-0.914)
Absolute Event Rate: 0.896% vs 0.891%
Abstract Objectives We aimed to (1) quantify changes in discrimination when adding intraoperative data to preoperative data and (2) compare tabular machine learning with feature engineering against a time-aware LSTM-based model. Materials and Methods Retrospective cohort of 46 204 adults undergoing 57 055 eligible noncardiac surgery in the INSPIRE database. We extracted 38 preoperative and 49 intraoperative variables; acute kidney injury (AKI) was defined by KDIGO serum creatinine criteria and modeled as stage 2/3 postoperative AKI. Models were trained on preoperative-only and combined pre- and intraoperative data. Intraoperative series were summarized using eight statistical features for tabular models or integrated directly using an MLP+LSTM architecture. Results GBT with combined features achieved the highest AUROC (0.896, 95% CI, 0.878-0.914), followed by combined AutoGluon (0.893, 95% CI, 0.877-0.909) and preoperative-only GBT (0.891, 95% CI, 0.871-0.910). ASA-PS ≥3 (AUROC 0.723, 95% CI, 0.700-0.746) and adapted GS-AKI (AUROC 0.719, 95% CI, 0.700-0.739) underperformed machine-learning models. The hybrid MLP+LSTM model did not outperform simpler tabular models (AUROC 0.870, 95% CI, 0.848-0.892). Discussion The small gain from adding low-frequency intraoperative summaries suggests that most discriminative information for stage 2/3 postoperative AKI was available before surgery. Conclusion Preoperative tabular ML models provided excellent prediction of postoperative AKI, and added limited incremental discrimination at the available sampling frequency. Future work should evaluate whether higher-frequency intraoperative signals better leverage time-aware architectures.
Do et al. (Tue,) conducted a cohort in Postoperative acute kidney injury (AKI) (n=46,204). Combined pre- and intraoperative data machine learning models vs. Preoperative-only machine learning models was evaluated on Stage 2/3 postoperative AKI (discrimination measured by AUROC) (AUROC 0.896, 95% CI 0.878-0.914). Machine learning models combining pre- and intraoperative data achieved an AUROC of 0.896 (95% CI 0.878-0.914) for predicting postoperative AKI, offering limited gain over preoperative data alone.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: